That's the only reason these models are good though. They don't one shot things. They get it wrong and then keep checking until they get it right. You gotta let them test
I would argue that the better you can “close the loop” the better. One of my favourite agent activities is giving it a firmware bug and JTAG access + a serial port. That setup means that flashing, debugging (inspecting variables and whatnot, setting breakpoints, etc), and logging can all happen completely autonomously.
Works especially well for transient/hard to repro bugs. It’ll either set breakpoints or write a monitoring script, go to sleep, get woken up by the harness when the bug trips, inspect state, put together a new build based on a hypothesis built from the debugging, flash it, and loop. I’ve had sessions run completely autonomously for over a day and come with a beautiful one-line solution to a gnarly race condition.
In that regard it’s like a human: you can read code all day if you want and you might get somewhere, but being able to inspect what happened, build a new theory, test it, and iterate is way more powerful 99% of the time.
I was trying to upload HDR photos to Instagram and couldn't figure out how to make it preserve the HDR-ness of my photos, and was going back and forth with an agent - step by step we'd slowly iterate on a photo, I'd upload, then I'd download the jpg and give it to the agent and it'd think, change something in the format, and we'd try again.
I got impatient and just said fuck it and gave it chrome-devtools and a blank instagram account and a test photo, and it figured the whole thing out in about a half hour. I built a little browser-based tool from what it discovered, and I use it to run my HDR photos through to format them correctly for instagram and it works a treat.
That's the only reason these models are good though. They don't one shot things. They get it wrong and then keep checking until they get it right. You gotta let them test
Agents prefer some sort of tests to check their output.
I would argue that the better you can “close the loop” the better. One of my favourite agent activities is giving it a firmware bug and JTAG access + a serial port. That setup means that flashing, debugging (inspecting variables and whatnot, setting breakpoints, etc), and logging can all happen completely autonomously.
Works especially well for transient/hard to repro bugs. It’ll either set breakpoints or write a monitoring script, go to sleep, get woken up by the harness when the bug trips, inspect state, put together a new build based on a hypothesis built from the debugging, flash it, and loop. I’ve had sessions run completely autonomously for over a day and come with a beautiful one-line solution to a gnarly race condition.
In that regard it’s like a human: you can read code all day if you want and you might get somewhere, but being able to inspect what happened, build a new theory, test it, and iterate is way more powerful 99% of the time.
This kind of approach works so well.
I was trying to upload HDR photos to Instagram and couldn't figure out how to make it preserve the HDR-ness of my photos, and was going back and forth with an agent - step by step we'd slowly iterate on a photo, I'd upload, then I'd download the jpg and give it to the agent and it'd think, change something in the format, and we'd try again.
I got impatient and just said fuck it and gave it chrome-devtools and a blank instagram account and a test photo, and it figured the whole thing out in about a half hour. I built a little browser-based tool from what it discovered, and I use it to run my HDR photos through to format them correctly for instagram and it works a treat.
1 reply →